Portfolio item number 1
Short description of portfolio item number 1
Short description of portfolio item number 1
Short description of portfolio item number 2
Published in Findings of the Association for Computational Linguistics (EMNLP 2023) , 2023
This paper proposes a novel approach, IICOT, that leverages generative models, instruction learning, and chain-of-thoughts to enhance reasoning capabilities for implicit discourse relation recognition, achieving state-of-the-art performance on benchmark datasets.
Published in Proceedings of the 33rd ACM International Conference on Information and Knowledge Management (CIKM 2024), 2024
This paper proposes a joint learning framework that combines prototypical learning, adversarial learning, and hub-migration based redistribution to enhance the performance of Pre-trained Language Models (PLMs) for implicit discourse relation recognition.
Published in Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) (ACL 2025), 2025
This paper introduces a Subtext-based Confidence-diagnosed Dual-channel Network (SCDN) for enhancing Implicit Discourse Relation Recognition (IDRR) by incorporating subtexts generated through LLaMA. The approach demonstrates significant improvements in recognizing semantic relations between argument pairs, highlighting the importance of subtexts as valuable contextual clues that enrich the understanding of implicit relations, ultimately resulting in higher F1-scores on benchmark datasets.
Published:
This is a description of your talk, which is a markdown files that can be all markdown-ified like any other post. Yay markdown!
Published:
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.
Undergraduate course, University 1, Department, 2014
This is a description of a teaching experience. You can use markdown like any other post.
Workshop, University 1, Department, 2015
This is a description of a teaching experience. You can use markdown like any other post.